Merging decision behavior model based on multivariate adaptive regression splines
LI Gen1, ZHAI Wei1, HUANG Haibo1, REN Jiaolong2, Wang Dengzhong3, WU Lan1
1. College of Auto and Traffic Engineering, Nanjing Forestry University, Nanjing 210037, China; 2. School of Civil and Architectural Engineering, Shandong University of Technology, Zibo 255000, China; 3. Zhejiang Scientific Research Institute of Transport, Hangzhou 310023, China
Abstract：[Objective] Weaving areas are bottlenecks of freeways, and lane-changing behavior is one of the main reasons for the capacity decline and traffic congestion in weaving areas. Frequent merging behaviors may lead to traffic flow disturbance upstream from the weaving area, affect the normal running of surrounding vehicles, and in severe cases may even lead to multi-vehicle accidents. An in-depth understanding of merging decision behavior in the weaving area is essential to reduce the vehicle collision risk and improve the traffic safety level. A newly developed nonparametric regression model-multiple adaptive regression splines (MARS)-is adopted to model the gap selection decision during merging to study the merging behavior in the freeway weaving area.[Methods] This study investigates complex interactions between merging and surrounding vehicles during merging. Trajectory data are extracted from the US-101 dataset provided by the dataset of next generation simulation program, and the symmetric exponential moving average filter method is used to smooth the data. Merging vehicles are influenced by surrounding vehicles in the auxiliary and adjacent main lanes. Thus, explanatory variables such as speeds, speed differences, gaps, and locations are calculated. Longitudinal and lateral collision risk indicators and time-to-collision are also considered to study the influence of collision risk on merging behaviors. Finally, 925 observations are obtained and randomly divided into two subdatasets to train and test the model. The MARS model is compared with four state-of-the-art machine learning techniques:classification and regression tree, gradient boosting decision tree (GBDT), random forest, and logistic regression models.[Results] The speed difference between the merging vehicle and vehicles in the adjacent main lane played the most important role in gap selection. Interactions of influencing variables were observed. In particular, the best interaction level was 4 in the final model. The comparison showed that GBDT and MARS had the lowest rates of prediction error at 0.138 and 0.141, respectively.However, MARS could provide explicit expression functions that reflect the interaction between the influencing variables, which was beneficial to engineering applications.[Conclusions] By using the optimal variable transformation and potential variable interaction in the regression modeling scheme, MARS could easily handle complex nonlinear relationships in merging behaviors. This model could accurately predict the gap selection behavior and provide explicit expression functions, thus simplifying its understanding and application to driver assistance systems and autonomous driving systems.
[1] CHEN D J, AHN S. Capacity-drop at extended bottlenecks:Merge, diverge, and weave[J]. Transportation Research Part B:Methodological, 2018, 108:1-20. [2] ZHENG Z D, AHN S, MONSERE C M. Impact of traffic oscillations on freeway crash occurrences[J]. Accident Analysis & Prevention, 2010, 42(2):626-636. [3] GIPPS P G. A model for the structure of lane-changing decisions[J]. Transportation Research Part B:Methodological, 1986, 20(5):403-414. [4] YANG Q, KOUTSOPOULOS H N. A microscopic traffic simulator for evaluation of dynamic traffic management systems[J]. Transportation Research Part C:Emerging Technologies, 1996, 4(3):113-129. [5] SINGH K, LI B B. Discrete choice modelling for traffic densities with lane-change behaviour[J]. Procedia-Social and Behavioral Sciences, 2012, 43:367-374. [6] SUN J, OUYANG J X, YANG J H. Modeling and analysis of merging behavior at expressway on-ramp bottlenecks[J]. Transportation Research Record:Journal of the Transportation Research Board, 2014, 2421(1):74-81. [7] HOU Y, EDARA P, SUN C. Modeling mandatory lane changing using Bayes classifier and decision trees[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(2):674-655. [8] ZHENG J, SUZUKI K, FUJITA M. Predicting driver's lane-changing decisions using a neural network model[J]. Simulation Modelling Practice and Theory, 2014, 42:73-83. [9] MOTAMEDIDEHKORDI N, AMINI S, HOFFMANN S, et al. Modeling tactical lane-change behavior for automated vehicles:A supervised machine learning approach[C]//2017 IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS). Naples, Italy:IEEE, 2017:268-273. [10] DÍAZ-ÁLVAREZ A, CLAVIJO M, JIMÉNEZ F, et al. Modelling the human lane-change execution behaviour through multilayer perceptrons and convolutional neural networks[J]. Transportation Research Part F:Traffic Psychology and Behaviour, 2018, 56:134-148. [11] XIE D F, FANG Z Z, JIA B, et al. A data-driven lane-changing model based on deep learning[J]. Transportation Research Part C:Emerging Technologies, 2019, 106:41-60. [12] 王俊彦, 蔡骏宇. 基于RBF神经网络的车辆安全换道时机决策模型研究[J]. 重庆理工大学学报(自然科学版), 2019, 33(11):47-51, 80. WANG J Y, CAI J Y. Research on modelling vehicle safety lane-changing timing decision based on RBF neural network[J]. Journal of Chongqing Institute of Technology, 2019, 33(11):47-51, 80. (in Chinese) [13] 徐兵, 刘潇, 汪子扬, 等. 采用梯度提升决策树的车辆换道融合决策模型[J]. 浙江大学学报(工学版), 2019, 53(6):1171-1181. XU B, LIU X, WANG Z Y, et al. Fusion decision model for vehicle lane change with gradient boosting decision tree[J]. Journal of Zhejiang University (Engineering Science), 2019, 53(6):1171-1181. (in Chinese) [14] 曹波, 李永乐, 赵凯, 等. 基于行为识别的智能车纵向决策研究[J]. 交通运输系统工程与信息, 2020, 20(3):61-66. CAO B, LI Y L, ZHAO K, et al. Intelligent vehicle longitudinal decision making based on behavior recognition[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3):61-66. (in Chinese) [15] 崔洁茗, 余贵珍, 周彬, 等. 基于神经网络的车辆强制换道预测模型[J]. 北京航空航天大学学报, 2022, 48(5):890-897. CUI J M, YU G Z, ZHOU B, et al. Mandatory lane change decision-making model based on neural network[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(5):890-897. (in Chinese) [16] 赵树恩, 王金祥, 李玉玲. 基于多目标优化的智能车辆换道轨迹规划[J]. 交通运输工程学报, 2021, 21(2):232-242. ZHAO S E, WANG J X, LI Y L. Lane changing trajectory planning of intelligent vehicle based on multiple objective optimization[J]. Journal of Traffic and Transportation Engineering, 2021, 21(2):232-242. (in Chinese) [17] 李根, 翟伟, 邬岚, 等. 基于多元自适应回归样条的交织区合流交互作用研究[J]. 东南大学学报(自然科学版), 2022, 52(4):796-805. LI G, ZHAI W, WU L, et al. Research on merging interactions in weaving area based on multiple adaptive regression splines[J]. Journal of Southeast University (Natural Science Edition), 2022, 52(4):796-805. (in Chinese) [18] DAS A, KHAN N, AHMED M M. Nonparametric multivariate adaptive regression splines models for investigating lane-changing gap acceptance behavior utilizing strategic highway research program 2 naturalistic driving data[J]. Transportation Research Record:Journal of the Transportation Research Board, 2020, 2674(5):223-238. [19] PUNZO V, BORZACCHIELLO M T, CIUFFO B. On the assessment of vehicle trajectory data accuracy and application to the next generation simulation (NGSIM) program data[J]. Transportation Research Part C:Emerging Technologies, 2011, 19(6):1243-1262. [20] LI G, FANG S, MA J X, et al. Modeling merging acceleration and deceleration behavior based on gradient-boosting decision tree[J]. Journal of Transportation Engineering, Part A:Systems, 2020, 146(7):05020005. [21] LI M, LI Z B, XU C C, et al. Short-term prediction of safety and operation impacts of lane changes in oscillations with empirical vehicle trajectories[J]. Accident Analysis & Prevention, 2020, 135:105345.
2024, Vol. 64 
